Path: utzoo!utgpu!jarvis.csri.toronto.edu!cs.utexas.edu!samsung!munnari.oz.au!murtoa.cs.mu.oz.au!ditmela!yarra!melba.bby.oz.au!leo!gnb
From: gnb@bby.oz.au (Gregory N. Bond)
Newsgroups: comp.sys.ibm.pc.rt
Subject: Re: Risc System/6000
Message-ID: <1990Mar6.035512.1139@melba.bby.oz.au>
Date: 6 Mar 90 03:55:12 GMT
References: <542@arccs2.fed.FRB.GOV>
Sender: gnb@melba.bby.oz.au (Gregory N. Bond)
Followup-To: comp.sys.ibm.pc.rt
Organization: Burdett, Buckeridge and Young Ltd.
Lines: 27
In-Reply-To: m1phm02@fed.FRB.GOV's message of 23 Feb 90 20:55:25 GMT

In article <542@arccs2.fed.FRB.GOV> m1phm02@fed.FRB.GOV (Patrick H. McAllister) writes:

   A lot of discussion has been going on about the processor performance of
   these machines, but I would also be interested in knowing something about
   I/O performance. Does anybody out in netland have any information that 
   can be posted about the disk options? What types of disk, what types
   of controllers? Access time, transfer rates (in theory and in practice)?
   I/O performance would be an important consideration around here.

Disk I/O is _ALL_ SCSI.  Even the biggest machines.

Disks come in 5 sizes, 120Mb -> 857Mb.  Seek times down to 12.2 ms,
latency 6ms, transfer rate 1.2 to 3 MB/sec.

(Data from information pack handed out at Australian product launch)
-- 
Gregory Bond (gnb@melba.bby.oz), Burdett, Buckeridge & Young Ltd., Melbourne
The IBM dictionary: ``Open Systems'' - has a bastardized Unix and an optional
ethernet connector.
--
Gregory Bond, Burdett Buckeridge & Young Ltd, Melbourne, Australia
Internet: gnb@melba.bby.oz.au    non-MX: gnb%melba.bby.oz@uunet.uu.net
Uucp: {uunet,pyramid,ubc-cs,ukc,mcvax,prlb2,nttlab...}!munnari!melba.bby.oz!gnb
-- 
Gregory Bond, Burdett Buckeridge & Young Ltd, Melbourne, Australia
Internet: gnb@melba.bby.oz.au    non-MX: gnb%melba.bby.oz@uunet.uu.net
Uucp: {uunet,pyramid,ubc-cs,ukc,mcvax,prlb2,nttlab...}!munnari!melba.bby.oz!gnb